← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

safe-rlhf

github.com

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Open source

Visit github.comexternal siteGitHub1,621 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. rlhf-book

    Textbook on reinforcement learning from human feedback

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    2,509 stars

  2. rl-tools

    The Fastest Deep Reinforcement Learning Library

    github.comLibraryOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,055 stars

  3. drl-zh

    Deep Reinforcement Learning: Zero to Hero!

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    2,293 stars

  4. Karotte

    a framework for building robust RL envs

    github.comLibraryOpen source2 reactionslatest reaction

    Hacker News
    8 pts
    GitHub
    186 stars

  5. RLHF-Reward-Modeling

    Recipes to train reward model for RLHF.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,546 stars